CN110505583A - A kind of path matching algorithm based on bayonet data and signaling data - Google Patents
A kind of path matching algorithm based on bayonet data and signaling data Download PDFInfo
- Publication number
- CN110505583A CN110505583A CN201910666051.0A CN201910666051A CN110505583A CN 110505583 A CN110505583 A CN 110505583A CN 201910666051 A CN201910666051 A CN 201910666051A CN 110505583 A CN110505583 A CN 110505583A
- Authority
- CN
- China
- Prior art keywords
- data
- track
- vehicle
- mobile phone
- bayonet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/20—Services signaling; Auxiliary data signalling, i.e. transmitting data via a non-traffic channel
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/40—Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]
Abstract
The present invention provides a kind of path matching algorithm based on bayonet data and signaling data, which includes data prediction, space-time trajectory matching algorithm, data enhancing algorithm and for judging the whether matched disaggregated model of track of vehicle and mobile phone track.The invalid data that different data is concentrated first removes, and the vehicle and cell phone apparatus of frequent activity are filtered out by calculating comentropy；Then the potential matched data collection of vehicle and mobile phone is obtained according to a kind of space-time trajectory matching algorithm, is matched further according to the long-time tracking to vehicle and mobile phone track with obtaining vehicle with the determination of mobile phone；Expansion sample is carried out to determining matching track followed by data enhancing algorithm；Path matching finally is utilized as a result, selecting the reasonable aspect of model, establishes track disaggregated model.The present invention is applied to the matching of magnanimity track of vehicle and mobile phone signaling track, solves the problems such as current path matching computational efficiency is poor, measurement index is single.
Description
Technical field
The present invention relates to path matching algorithm field, more particularly, to a kind of based on bayonet data and signaling data
Path matching algorithm.
Background technique
In recent years, with the development of location technology, a large amount of individual track data occurs.The track of vehicle can pass through fixation
Position sensor is recorded, such as the automatic Vehicle License Plate Recognition System on road monitoring bayonet.It from colored, black and white or infrared can take the photograph
The license plate number of vehicle is identified in the image of camera shooting.The data that track of vehicle can be recorded according to bayonet are reconstructed.It removes
Outside fixed position sensor, mobile traffic sensor can follow vehicle to move together, they include probe vehicles, GPS device
With mobile phone etc..Mobile phone when making a phone call or surfing the Internet, can and neighbouring base station generate connection, when base station will record lower current
Between, the data such as position and device numbering, the detailed motion track of cell phone apparatus or individual can be restored by these data.
Based on vehicle millions of in city and mobile phone track data, most phase is found out from the data set of two isomeries
As track pair, be the equal of matching the driver in city with vehicle, this will have sizable application value, can be
Resident trip pattern-recognition, the analysis of urban inner vehicle restricted driving policy implication, the research fields such as private data publication provide theoretical
With reference to.
Propose many track similarity calculating methods both at home and abroad at present, can be divided mainly into space similarity and when Kongxiang
Like degree two major classes.Space similarity is mainly to find the track with similar geometry shape, and has ignored time dimension, when Kongxiang
Then consider time and the spatial character of track simultaneously like degree.However, these algorithms need every two tracks just to calculate primary phase
Like degree, for track millions of in city, computing cost is too big for this, and often evaluates using only an index
The similarity of track can not completely describe the similar characteristic of track.
Summary of the invention
The present invention provides a kind of path matching algorithm based on bayonet data and signaling data, which is magnanimity isomery rail
The matching of mark provides the calculation method that a kind of computation complexity is smaller, evaluation index is more, more reasonable.
In order to reach above-mentioned technical effect, technical scheme is as follows:
A kind of path matching algorithm based on bayonet data and signaling data, comprising the following steps:
S1: the road gate monitoring data collection and mobile phone signaling data collection in survey region and search time section are obtained；
S2: pre-processing bayonet data set and signaling data collection, including invalid data cleaning, time span screening with
And frequently motion track screening；
S3: the potential matched data collection of vehicle and mobile phone is obtained by space-time trajectory matching algorithm；
S4: matching vehicle and the mobile phone track in different time period that potential matched data is concentrated, if when
Between in range, the matching relationship that vehicle and mobile phone track maintain like can illustrate that the vehicle with the mobile phone is to determine to match；
S5: determining matching track is sampled using data enhancing algorithm, is matched with obtaining more vehicles with mobile phone
Positive example；Vehicle and mobile phone track are randomly selected from bayonet and signaling data concentration, and chooses the vehicle and mobile phone of erroneous matching
Track is as vehicle and the matched counter-example of mobile phone；
S6: the reasonable aspect of model and the higher sorting algorithm of accuracy rate, the positive example obtained based on above-mentioned steps are used
Track disaggregated model is established with counter-example track data.
Further, in the step S1, mobile phone signaling data includes: (1) Customs Assigned Number isdn: mobile phone user's is unique
Mark；(2) longitude lng: the longitude of user position；(3) latitude lat: the latitude of user position；(4) time time:
The time that signaling record generates.The bayonet monitoring data include: (1) bayonet number kdbh: monitoring the unique identification of bayonet；
(2) longitude kkjd: the longitude of bayonet is monitored；(3) latitude kkwd: the latitude of bayonet is monitored；(4) number plate of vehicle hphm: by card
The license plate number of mouth vehicle；(5) cross vehicle time gcsj: vehicle passes through the time of bayonet.
Further, in the step S2, invalid data includes malposition data, i.e. the longitude and latitude of bayonet or signaling data
Degree is not in research range；The fields such as field missing data, i.e. time, longitude and latitude, number plate of vehicle have the data of missing；And it is wrong
Misidentify data, the specially incorrect data of number plate of vehicle of bayonet identification.
Further, in the step S2, time span screening is specially to choose the signaling and card of daily 6:00 to 24:00
Mouth data are calculated, and the data other than the period are rejected.
Further, in the step S2, the mobile frequent degree of track is the information entropy by calculating every track
It measures, the track for only selecting information entropy to be greater than threshold value carries out path matching calculating, and information entropy threshold is 2.Trace information entropy
The specific calculation of value are as follows:
Wherein, D is the motion track of a vehicle or mobile phone, and Ent (D) is the information entropy of the track, pkFor the track
In k-th of location point occur ratio, m be the track in different location point quantity.
Further, in the step S3, the detailed process of space-time trajectory matching algorithm are as follows:
A) motion track that one vehicle is extracted according to license plate number and excessively vehicle time from bayonet data set, tracing point
It arranges sequentially in time；
B) it takes a track of vehicle point as research object in order, searches for signaling data and concentrate with the presence or absence of with the vehicle
Centered on tracing point, meets time threshold τ and distance threshold ε is formed by the data of space-time restriction；
C) if it exists, just by all cell phone apparatus for meeting CFL stability condition to recording, as the latent of the vehicle
In mobile phone matched data collection；
D) next track of vehicle point is taken again, search whether there is the cell phone apparatus for meeting the tracing point space-time restriction, if
In the presence of, then the corresponding cell phone apparatus of two tracing points is sought common ground, if it does not exist or intersection be sky, then the vehicle match fail；
If potential mobile phone matched data collection is not empty, then vehicle match success e) to the last one tracing point.
Time threshold τ in algorithm is 600 seconds, and distance threshold ε is 2000 meters.
Further, in the step S4, time range is one week or one week or more, determines that matching refers to that the mobile phone is
Cell phone apparatus entrained by corresponding vehicle driver.
Further, in the step S5, data enhance the detailed process of algorithm are as follows:
A) it chooses and determines matched vehicle and mobile phone track, several points are randomly selected from track of vehicle point, form one
The new track of vehicle of item；
B) for new track of vehicle, the signaling for meeting new vehicle track space-time restriction is chosen from corresponding mobile phone track
Data point forms a new mobile phone signaling track；
C) track of vehicle that sampling obtains can be used as new determination with signaling track and match track pair.
Further, in the step S6, when the aspect of model is the shortest distance (CPD), Hausdorff distance (HD), dynamic
Between regular distance (DTW), maximum public substring (LCSS) and editing distance (EDR).
Further, in the step S6, sorting algorithm be LightGBM algorithm, be one it is quick, distributed,
The high performance gradient boosting algorithm based on decision Tree algorithms.
Compared with prior art, the beneficial effect of technical solution of the present invention is:
1, traditional similarity calculating method is to enumerate their similarity of any two trajectory calculations, this is in city
For millions of mobile phone users and vehicle, it will need a large amount of computing resource that can complete matching degree calculating.The method of the present invention
The matching primitives efficiency of magnanimity isomery track is improved, is first rejected mobile track infrequently by trace information entropy,
Secondly a large amount of dissimilar track is also quickly excluded using CFL stability condition in space-time trajectory matching algorithm, this can subtract
Few a large amount of computing cost, reduces and calculates the time.
2, the currently used algorithm for finding similar track only accounts for single index of similarity, and the method for the present invention combines
The index of similarity of multiple classics, constructs the disaggregated model based on LightGBM algorithm, and model can be described more completely out
The space-time characterisation of track, and effectively judge two given isomery tracks with the presence or absence of matching relationship.
Detailed description of the invention
Fig. 1 is flow diagram of the present invention.
Specific embodiment
The attached figures are only used for illustrative purposes and cannot be understood as limitating the patent；
In order to better illustrate this embodiment, the certain components of attached drawing have omission, zoom in or out, and do not represent actual product
Size；
To those skilled in the art, it is to be understood that certain known features and its explanation, which may be omitted, in attached drawing
's.
The following further describes the technical solution of the present invention with reference to the accompanying drawings and examples.
Embodiment 1
As shown in Figure 1, a kind of path matching algorithm based on bayonet data and signaling data, comprising the following steps:
S1: the road gate monitoring data collection and mobile phone signaling data collection in survey region and search time section are obtained；
S2: pre-processing bayonet data set and signaling data collection, including invalid data cleaning, time span screening with
And frequently motion track screening；
S3: the potential matched data collection of vehicle and mobile phone is obtained by space-time trajectory matching algorithm；
S4: matching vehicle and the mobile phone track in different time period that potential matched data is concentrated, if when
Between in range, the matching relationship that vehicle and mobile phone track maintain like can illustrate that the vehicle with the mobile phone is to determine to match；
S5: determining matching track is sampled using data enhancing algorithm, is matched with obtaining more vehicles with mobile phone
Positive example；Vehicle and mobile phone track are randomly selected from bayonet and signaling data concentration, and chooses the vehicle and mobile phone of erroneous matching
Track is as vehicle and the matched counter-example of mobile phone；
S6: using rational model feature and the higher sorting algorithm of accuracy rate, the positive example obtained based on above-mentioned steps with
Counter-example track data establishes track disaggregated model.
Above-mentioned each step is described in detail below.
Firstly, it is necessary to obtain all road gates and mobile phone base in survey region such as local administrative area or administrative areas at the county level
One week or more the record data stood.
Secondly, being pre-processed to vehicle bayonet data and mobile phone signaling data:
A) data by latitude and longitude coordinates not in survey region are deleted；It is the data of null value or invalid value by field information
It deletes；To the regulation of automotive number plate, leave out bayonet number according to " People's Republic of China's automotive number plate " (GA 36-2007)
According to the data for concentrating wrong number plate.
B) it concentrates the data of daily 0:00-6:00 to reject vehicle bayonet data set and mobile phone signaling data, is not involved in rail
Mark matching primitives.
C) it is numbered by license plate number, cell phone apparatus and the record time filters out the daily of each vehicle and each mobile phone
Track calculates its information entropy according to the geographical location of tracing point in each track, and calculation formula is as follows:
Wherein, D is the motion track of a vehicle or mobile phone, and Ent (D) is the information entropy of the track, pkFor the track
In k-th of location point occur ratio, m be the track in different location point quantity.
If the information entropy of this track is left out less than 2, by it from corresponding data concentration, it is not involved in path matching meter
It calculates.
Then, the bayonet data set and signaling data collection for taking a certain day in research range carry out space-time trajectory matching algorithm fortune
It calculates.
A) the motion track c that one vehicle is extracted according to license plate number and excessively vehicle time from bayonet data set, track
Point arranges sequentially in time；
B) a track of vehicle point lc is taken in order1As research object, searches for signaling data and concentrate with the presence or absence of with this
Centered on track of vehicle point, meets time threshold τ and distance threshold ε is formed by the data of space-time restriction, space-time restriction is as follows
It is shown:
(lc.x- ε, lc.y- ε, lc.t- τ)≤(ls.x, ls.y, ls.t)≤(lc.x+ ε, lc.y+ ε, lc.t+ τ)
C) meet the signaling data ls of space-time restriction if it exists, just recorded the corresponding cell phone apparatus in these tracks
Come, the potential mobile phone matched data collection cs as the vehicle1；
D) next track of vehicle point lc is taken again2, search is with the presence or absence of the cell phone apparatus for meeting the tracing point space-time restriction
cs2, and if it exists, then the corresponding cell phone apparatus of two tracing points is sought common ground, if it does not exist or intersection is sky, i.e.,OrThen the vehicle match fails；
If potential mobile phone matched data collection is not empty, then vehicle match success e) to the last one tracing point.
Then, for a certain vehicle, if certain mobile phone appears at its potential mobile phone coupling number within one week seven days
According to concentration, that is, think that the vehicle is matched with the mobile phone for determination, i.e., the mobile phone is that the portable movement of the vehicle driver is set
It is standby.
Then, certain track of vehicle c=(lc matched for determination1, lc2, lc3, lc4, lc5, lc6) and certain mobile phone signaling rail
Mark s=(ls1, ls2, ls3, ls4, ls5, ls6), 3 points are randomly selected from track of vehicle, obtain a new track of vehicleFurther according to space-time restriction relationship, corresponding new mobile phone signaling track is obtained
New vehicle can be obtained in this way and match positive example with mobile phone；Vehicle and mobile phone rail are randomly selected from bayonet and signaling data concentration again
Mark, and the vehicle for choosing erroneous matching and mobile phone track are as vehicle and the matched counter-example of mobile phone.
Finally, calculate separately matching positive example and the different characteristic value that matches counter-example, including the shortest distance (CPD), bold and unconstrained this is more
Husband's distance (HD), dynamic time warping distance (DTW), maximum public substring (LCSS) and editing distance (EDR), form such as table
Data set shown in 1.
1 data set schematic table of table
| ID | hphm | isdn | CPD | SPD | DTW | LCSS | EDR | Label |
| 1 | @#$E8 | 5ea3bd | 38.80 | 2354 | 397.66 | 5 | 46 | 1 |
| 2 | $ %#91 | 2fb9df | 42.48 | 3812 | 266.43 | 3 | 47 | 0 |
| 3 | ！#$@19 | ed2e83. | 19.16 | 227 | 237.84 | 7 | 51 | 1 |
70% data are randomly selected from data set as training set, are inputted LightGBM model and are trained, to surplus
Under 30% data predicted.
The same or similar label correspond to the same or similar components；
Described in attached drawing positional relationship for only for illustration, should not be understood as the limitation to this patent；
Obviously, the above embodiment of the present invention be only to clearly illustrate example of the present invention, and not be pair
The restriction of embodiments of the present invention.For those of ordinary skill in the art, may be used also on the basis of the above description
To make other variations or changes in different ways.There is no necessity and possibility to exhaust all the enbodiments.It is all this
Made any modifications, equivalent replacements, and improvements etc., should be included in the claims in the present invention within the spirit and principle of invention
Protection scope within.
Claims (10)
1. a kind of path matching algorithm based on bayonet data and signaling data, which comprises the following steps:
S1: the road gate monitoring data collection and mobile phone signaling data collection in survey region and search time section are obtained；
S2: pre-processing bayonet data set and signaling data collection, including invalid data cleaning, time span screening and frequency
Numerous motion track screening；
S3: the potential matched data collection of vehicle and mobile phone is obtained by space-time trajectory matching algorithm；
S4: vehicle and the mobile phone track in different time period that potential matched data is concentrated are matched, if in time model
In enclosing, the matching relationship that vehicle is maintained like with mobile phone track can illustrate that the vehicle is matched with the mobile phone for determination；
S5: determining matching track is sampled using data enhancing algorithm, matches positive example to obtain more vehicles with mobile phone；
Vehicle and mobile phone track are randomly selected from bayonet and signaling data concentration, and chooses the vehicle and mobile phone track work of erroneous matching
For vehicle and the matched counter-example of mobile phone；
S6: using the reasonable aspect of model and the higher sorting algorithm of accuracy rate, the positive example that is obtained based on above-mentioned steps and anti-
Example track data establishes track disaggregated model.
2. the path matching algorithm according to claim 1 based on bayonet data and signaling data, which is characterized in that described
Mobile phone signaling data in step S1 includes: (1) Customs Assigned Number isdn: the unique identification of mobile phone user；(2) longitude lng: user
The longitude of position；(3) latitude lat: the latitude of user position；(4) time time: the time that signaling record generates.
The bayonet monitoring data include: (1) bayonet number kdbh: monitoring the unique identification of bayonet；(2) longitude kkjd: monitoring card
The longitude of mouth；(3) latitude kkwd: the latitude of bayonet is monitored；(4) number plate of vehicle hphm: by the license plate number of bayonet vehicle；(5)
Cross vehicle time gcsj: vehicle passes through the time of bayonet.
3. the path matching algorithm according to claim 2 based on bayonet data and signaling data, which is characterized in that described
In step S2, invalid data includes malposition data, i.e., the longitude and latitude of bayonet or signaling data is not in research range；Field
The fields such as missing data, i.e. time, longitude and latitude, number plate of vehicle have the data of missing；And wrong identification data, specially bayonet
The incorrect data of the number plate of vehicle of identification.
4. the path matching algorithm according to claim 3 based on bayonet data and signaling data, which is characterized in that described
In step S2, the signaling that daily 6:00 to 24:00 is specially chosen in time span screening is calculated with bayonet data, the time
Data other than section are rejected.
5. the path matching algorithm according to claim 4 based on bayonet data and signaling data, which is characterized in that described
In step S2, the mobile frequent degree of track is measured by calculating the information entropy of every track, only selects information entropy
Track greater than threshold value carries out path matching calculating, and information entropy threshold is 2.The specific calculation of trace information entropy are as follows:
Wherein, D is the motion track of a vehicle or mobile phone, and Ent (D) is the information entropy of the track, pkFor kth in the track
The ratio that a location point occurs, m are the quantity of different location point in the track.
6. the path matching algorithm according to claim 5 based on bayonet data and signaling data, which is characterized in that described
In step S3, the detailed process of space-time trajectory matching algorithm are as follows:
A) according to license plate number and spend the vehicle time from bayonet data set and extract the motion track of a vehicle, tracing point according to
Time sequencing arrangement；
B) it takes a track of vehicle point as research object in order, searches for signaling data and concentrate with the presence or absence of with the track of vehicle
Centered on point, meets time threshold τ and distance threshold ε is formed by the data of space-time restriction；
C) if it exists, just all cell phone apparatus for meeting CFL stability condition are recorded, the potential hand as the vehicle
Machine matched data collection；
D) next track of vehicle point is taken again, and search is with the presence or absence of the cell phone apparatus for meeting the tracing point space-time restriction, and if it exists,
Then the corresponding cell phone apparatus of two tracing points is sought common ground, if it does not exist or intersection is sky, then the vehicle match fails；
If potential mobile phone matched data collection is not empty, then vehicle match success e) to the last one tracing point.
Time threshold τ in algorithm is 600 seconds, and distance threshold ε is 2000 meters.
7. the path matching algorithm according to claim 6 based on bayonet data and signaling data, which is characterized in that described
In step S4, time range is one week or one week or more, determines that matching refers to the mobile phone for entrained by corresponding vehicle driver
Cell phone apparatus.
8. the path matching algorithm according to claim 7 based on bayonet data and signaling data, which is characterized in that described
In step S5, data enhance the detailed process of algorithm are as follows:
A) it chooses and determines matched vehicle and mobile phone track, several points are randomly selected from track of vehicle point, form one newly
Track of vehicle；
B) for new track of vehicle, the signaling data for meeting new vehicle track space-time restriction is chosen from corresponding mobile phone track
Point forms a new mobile phone signaling track；
C) track of vehicle that sampling obtains can be used as new determination with signaling track and match track pair.
9. the path matching algorithm according to claim 8 based on bayonet data and signaling data, which is characterized in that described
In step S6, the aspect of model is the shortest distance (CPD), Hausdorff distance (HD), dynamic time warping are apart from (DTW), maximum
Public substring (LCSS) and editing distance (EDR).
10. the path matching algorithm according to claim 9 based on bayonet data and signaling data, which is characterized in that institute
It states in step S6, sorting algorithm is LightGBM algorithm, is one quick, distributed, high performance based on decision tree
The gradient boosting algorithm of algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910666051.0A CN110505583B (en) | 2019-07-23 | 2019-07-23 | Trajectory matching method based on bayonet data and signaling data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910666051.0A CN110505583B (en) | 2019-07-23 | 2019-07-23 | Trajectory matching method based on bayonet data and signaling data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110505583A true CN110505583A (en) | 2019-11-26 |
| CN110505583B CN110505583B (en) | 2021-01-22 |
Family
ID=68586670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910666051.0A Active CN110505583B (en) | 2019-07-23 | 2019-07-23 | Trajectory matching method based on bayonet data and signaling data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110505583B (en) |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111417088A (en) * | 2020-03-25 | 2020-07-14 | 商车云(北京)科技有限公司 | Internet of vehicles data identity attribute authentication method |
| CN111523577A (en) * | 2020-04-13 | 2020-08-11 | 南京烽火星空通信发展有限公司 | Mass trajectory similarity calculation method based on improved LCSS algorithm |
| CN111521191A (en) * | 2020-04-20 | 2020-08-11 | 中国农业科学院农业信息研究所 | Mobile phone user moving path map matching method based on signaling data |
| CN111950937A (en) * | 2020-09-01 | 2020-11-17 | 上海海事大学 | Key personnel risk assessment method based on fusion space-time trajectory |
| CN112511971A (en) * | 2020-11-26 | 2021-03-16 | 西安建筑科技大学 | Travel mode identification method based on mobile phone signaling data |
| CN112634457A (en) * | 2021-01-06 | 2021-04-09 | 广西科技大学 | Point cloud simplification method based on local entropy of Hausdorff distance and average projection distance |
| CN112672288A (en) * | 2020-12-15 | 2021-04-16 | 佳都新太科技股份有限公司 | Vehicle track prediction method and device based on checkpoint recording |
| CN112734219A (en) * | 2021-01-05 | 2021-04-30 | 中交智运有限公司 | Vehicle transportation driving behavior analysis method and system |
| CN112785223A (en) * | 2021-01-05 | 2021-05-11 | 中交智运有限公司 | Space-time trajectory matching method and system based on Beidou positioning and mobile signaling |
| CN113160551A (en) * | 2021-01-12 | 2021-07-23 | 北京品恩科技股份有限公司 | Traffic big data based accompanying model application method |
| CN113487865A (en) * | 2021-07-02 | 2021-10-08 | 江西锦路科技开发有限公司 | System and method for acquiring information of vehicles running on highway |
| CN113723316A (en) * | 2021-09-01 | 2021-11-30 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN113806465A (en) * | 2021-09-22 | 2021-12-17 | 公安部交通管理科学研究所 | Bayonet position longitude and latitude deviation correction method based on new energy automobile track data |
| CN114372382A (en) * | 2022-03-22 | 2022-04-19 | 交通运输部公路科学研究所 | Method, device and storage medium for evaluating reliability of vehicle track |
| CN114390459A (en) * | 2021-12-27 | 2022-04-22 | 安徽百诚慧通科技有限公司 | Method for identifying illegal and excessive person carrying of agricultural vehicle and storage medium |
| CN114416710A (en) * | 2021-12-29 | 2022-04-29 | 苏州大学 | Method and system for extracting OD position of express way vehicle |
| CN115877343A (en) * | 2023-02-02 | 2023-03-31 | 中电信数字城市科技有限公司 | Man-vehicle matching method and device based on radar target tracking and electronic equipment |
| CN116258488A (en) * | 2023-03-17 | 2023-06-13 | 中远海运科技股份有限公司 | Data preprocessing method and system for accurately restoring actual passing track of vehicle |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462193A (en) * | 2014-10-28 | 2015-03-25 | 上海市政工程设计研究总院（集团）有限公司 | Vehicle movement trajectory searching system and method based on time-space matching |
| CN106303962A (en) * | 2016-08-17 | 2017-01-04 | 公安部道路交通安全研究中心 | A kind of method and system realizing people's car information association |
| US20170091272A1 (en) * | 2015-09-30 | 2017-03-30 | International Business Machines Corporation | Precision Adaptive Vehicle Trajectory Query Plan Optimization |
| EP3376390A1 (en) * | 2017-03-17 | 2018-09-19 | TTTech Computertechnik AG | Fault tolerant method for controlling an autonomous controlled object |
| CN108629978A (en) * | 2018-06-07 | 2018-10-09 | 重庆邮电大学 | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network |
| CN109344725A (en) * | 2018-09-04 | 2019-02-15 | 上海交通大学 | A kind of online tracking of multirow people based on space-time attention rate mechanism |
| CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
| US20190180610A1 (en) * | 2017-06-29 | 2019-06-13 | Shandong Provincial Communications Planning And Design Institute | Vehicle type identification method and device based on mobile phone data |
-
2019
- 2019-07-23 CN CN201910666051.0A patent/CN110505583B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104462193A (en) * | 2014-10-28 | 2015-03-25 | 上海市政工程设计研究总院（集团）有限公司 | Vehicle movement trajectory searching system and method based on time-space matching |
| US20170091272A1 (en) * | 2015-09-30 | 2017-03-30 | International Business Machines Corporation | Precision Adaptive Vehicle Trajectory Query Plan Optimization |
| CN106303962A (en) * | 2016-08-17 | 2017-01-04 | 公安部道路交通安全研究中心 | A kind of method and system realizing people's car information association |
| EP3376390A1 (en) * | 2017-03-17 | 2018-09-19 | TTTech Computertechnik AG | Fault tolerant method for controlling an autonomous controlled object |
| US20190180610A1 (en) * | 2017-06-29 | 2019-06-13 | Shandong Provincial Communications Planning And Design Institute | Vehicle type identification method and device based on mobile phone data |
| CN108629978A (en) * | 2018-06-07 | 2018-10-09 | 重庆邮电大学 | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network |
| CN109344725A (en) * | 2018-09-04 | 2019-02-15 | 上海交通大学 | A kind of online tracking of multirow people based on space-time attention rate mechanism |
| CN109635059A (en) * | 2018-11-23 | 2019-04-16 | 武汉烽火众智数字技术有限责任公司 | People's vehicle association analysis method and system based on track similarity mode |
Non-Patent Citations (3)
| Title |
|---|
| HUA XUE: "《UPS: Combatting Urban Vehicle Localization with Cellular-Aware Trajectories》", 《2016 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM)》 * |
| 吕遒健: "《基于无线网络流量的用户移动性分析与应用》", 《中国博士学位论文全文数据库》 * |
| 蔡正义: "《基于大数据的城市居民出行分析建模》", 《中国博士学位论文全文数据库》 * |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111417088B (en) * | 2020-03-25 | 2024-03-15 | 商车云(北京)科技有限公司 | Identity attribute authentication method for Internet of vehicles data |
| CN111417088A (en) * | 2020-03-25 | 2020-07-14 | 商车云(北京)科技有限公司 | Internet of vehicles data identity attribute authentication method |
| CN111523577A (en) * | 2020-04-13 | 2020-08-11 | 南京烽火星空通信发展有限公司 | Mass trajectory similarity calculation method based on improved LCSS algorithm |
| CN111521191A (en) * | 2020-04-20 | 2020-08-11 | 中国农业科学院农业信息研究所 | Mobile phone user moving path map matching method based on signaling data |
| CN111950937B (en) * | 2020-09-01 | 2023-12-01 | 上海海事大学 | Important personnel risk assessment method based on fusion of space-time trajectories |
| CN111950937A (en) * | 2020-09-01 | 2020-11-17 | 上海海事大学 | Key personnel risk assessment method based on fusion space-time trajectory |
| CN112511971A (en) * | 2020-11-26 | 2021-03-16 | 西安建筑科技大学 | Travel mode identification method based on mobile phone signaling data |
| CN112672288A (en) * | 2020-12-15 | 2021-04-16 | 佳都新太科技股份有限公司 | Vehicle track prediction method and device based on checkpoint recording |
| CN112672288B (en) * | 2020-12-15 | 2022-11-04 | 佳都科技集团股份有限公司 | Vehicle track prediction method and device based on checkpoint recording |
| CN112785223A (en) * | 2021-01-05 | 2021-05-11 | 中交智运有限公司 | Space-time trajectory matching method and system based on Beidou positioning and mobile signaling |
| CN112734219A (en) * | 2021-01-05 | 2021-04-30 | 中交智运有限公司 | Vehicle transportation driving behavior analysis method and system |
| CN112785223B (en) * | 2021-01-05 | 2022-06-07 | 中交智运有限公司 | Space-time trajectory matching method and system based on Beidou positioning and mobile signaling |
| CN112734219B (en) * | 2021-01-05 | 2023-07-21 | 中交智运有限公司 | Vehicle transportation running behavior analysis method and system |
| CN112634457A (en) * | 2021-01-06 | 2021-04-09 | 广西科技大学 | Point cloud simplification method based on local entropy of Hausdorff distance and average projection distance |
| CN112634457B (en) * | 2021-01-06 | 2022-07-05 | 广西科技大学 | Point cloud simplification method based on local entropy of Hausdorff distance and average projection distance |
| CN113160551A (en) * | 2021-01-12 | 2021-07-23 | 北京品恩科技股份有限公司 | Traffic big data based accompanying model application method |
| CN113487865A (en) * | 2021-07-02 | 2021-10-08 | 江西锦路科技开发有限公司 | System and method for acquiring information of vehicles running on highway |
| CN113487865B (en) * | 2021-07-02 | 2022-07-22 | 江西锦路科技开发有限公司 | System and method for acquiring information of vehicles running on highway |
| CN113723316B (en) * | 2021-09-01 | 2024-04-16 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN113723316A (en) * | 2021-09-01 | 2021-11-30 | 杭州智诚惠通科技有限公司 | Vehicle identification method, device, equipment and storage medium |
| CN113806465A (en) * | 2021-09-22 | 2021-12-17 | 公安部交通管理科学研究所 | Bayonet position longitude and latitude deviation correction method based on new energy automobile track data |
| CN114390459A (en) * | 2021-12-27 | 2022-04-22 | 安徽百诚慧通科技有限公司 | Method for identifying illegal and excessive person carrying of agricultural vehicle and storage medium |
| WO2023123616A1 (en) * | 2021-12-29 | 2023-07-06 | 苏州大学 | Method and system for extracting od positions of vehicle on expressway |
| CN114416710A (en) * | 2021-12-29 | 2022-04-29 | 苏州大学 | Method and system for extracting OD position of express way vehicle |
| CN114372382B (en) * | 2022-03-22 | 2022-06-10 | 交通运输部公路科学研究所 | Method, device and storage medium for evaluating reliability of vehicle track |
| CN114372382A (en) * | 2022-03-22 | 2022-04-19 | 交通运输部公路科学研究所 | Method, device and storage medium for evaluating reliability of vehicle track |
| CN115877343A (en) * | 2023-02-02 | 2023-03-31 | 中电信数字城市科技有限公司 | Man-vehicle matching method and device based on radar target tracking and electronic equipment |
| CN116258488A (en) * | 2023-03-17 | 2023-06-13 | 中远海运科技股份有限公司 | Data preprocessing method and system for accurately restoring actual passing track of vehicle |
| CN116258488B (en) * | 2023-03-17 | 2024-01-26 | 中远海运科技股份有限公司 | Data preprocessing method and system for accurately restoring actual passing track of vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110505583B (en) | 2021-01-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110505583A (en) | A kind of path matching algorithm based on bayonet data and signaling data | |
| Tang et al. | CLRIC: Collecting lane-based road information via crowdsourcing | |
| Li et al. | Large-scale joint map matching of GPS traces | |
| Chang et al. | Deepvp: Deep learning for vanishing point detection on 1 million street view images | |
| CN102102992B (en) | Multistage network division-based preliminary screening method for matched roads and map matching system | |
| CN108629978A (en) | A kind of traffic trajectory predictions method based on higher-dimension road network and Recognition with Recurrent Neural Network | |
| Yang et al. | Automatic change detection in lane-level road networks using GPS trajectories | |
| CN109815993B (en) | GPS track-based regional feature extraction, database establishment and intersection identification method | |
| Yin et al. | Feature-based map matching for low-sampling-rate GPS trajectories | |
| Ji et al. | A method for LSTM-based trajectory modeling and abnormal trajectory detection | |
| Zand et al. | Multiscale crowd counting and localization by multitask point supervision | |
| Cao et al. | Walkway discovery from large scale crowdsensing | |
| CN111666823B (en) | Pedestrian re-identification method based on individual walking motion space-time law collaborative identification | |
| CN103699677A (en) | Criminal track map drawing system and method based on face recognition | |
| CN111935450A (en) | Intelligent suspect tracking method and system and computer readable storage medium | |
| Zhu et al. | Learning transportation annotated mobility profiles from GPS data for context-aware mobile services | |
| Yang et al. | GPS and acceleration data in multimode trip data recognition based on wavelet transform modulus maximum algorithm | |
| CN105355047B (en) | The Data Fusion method of many Vehicle Detection source dynamic time granularities | |
| Hashemi | Reusability of the output of map-matching algorithms across space and time through machine learning | |
| Cheng et al. | Pedestrian group detection in shared space | |
| CN112365708A (en) | Scenic spot traffic volume prediction model establishing and predicting method based on multi-graph convolution network | |
| CN114708521A (en) | City functional area identification method and system based on street view image target relation perception network | |
| Raymond et al. | Bus trajectory identification by map-matching | |
| Li et al. | A trajectory restoration algorithm for low-sampling-rate floating car data and complex urban road networks | |
| CN107045630A (en) | A kind of pedestrian detection and personal identification method and system based on RGBD |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |